diff --git a/.gitattributes b/.gitattributes index 53d7257..68ceed1 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,47 +1,37 @@ *.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text -*.bin.* filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text -*.zstandard filter=lfs diff=lfs merge=lfs -text -*.tfevents* filter=lfs diff=lfs merge=lfs -text -*.db* filter=lfs diff=lfs merge=lfs -text -*.ark* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text -*.safetensors filter=lfs diff=lfs merge=lfs -text -*.ckpt filter=lfs diff=lfs merge=lfs -text -*.gguf* filter=lfs diff=lfs merge=lfs -text -*.ggml filter=lfs diff=lfs merge=lfs -text -*.llamafile* filter=lfs diff=lfs merge=lfs -text -*.pt2 filter=lfs diff=lfs merge=lfs -text -*.mlmodel filter=lfs diff=lfs merge=lfs -text -*.npy filter=lfs diff=lfs merge=lfs -text -*.npz filter=lfs diff=lfs merge=lfs -text -*.pickle filter=lfs diff=lfs merge=lfs -text -*.pkl filter=lfs diff=lfs merge=lfs -text -*.tar filter=lfs diff=lfs merge=lfs -text -*.wasm filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text -*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file +*tfevents* filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +pytorch_model.bin filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index af5a41a..601df1f 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,53 @@ --- -license: Apache License 2.0 - -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm +license: apache-2.0 +datasets: +- cerebras/SlimPajama-627B +- bigcode/starcoderdata +- teknium/openhermes +language: +- en --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope -``` -```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('cognitivecomputations/TinyDolphin-2.8.2-1.1b') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/cognitivecomputations/TinyDolphin-2.8.2-1.1b.git -``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +# TinyDolphin-2.8.2-1.1b + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/655dc641accde1bbc8b41aec/qUCZv8vxXDXi9r-9c0jvP.jpeg) + +Join Our Discord! https://discord.gg/vT3sktQ3zb + +This is an version 3 of a model trained on 3 3090's by Kearm on the new Dolphin 2.8 dataset by Eric Hartford https://erichartford.com/dolphin 🐬 + +For this version we refined the datasets used. + +## Example Outputs + +TBD + +Support my efforts! https://ko-fi.com/kearm + +# Orignal Model Card Below + +# TinyLlama-1.1B + + +https://github.com/jzhang38/TinyLlama + +The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. + +We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. + +#### This Collection +This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen. + +#### Eval + +| Model | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg | +|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----| +| Pythia-1.0B | 300B | 47.16 | 31.40| 53.43 | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 | +| TinyLlama-1.1B-intermediate-step-50K-104b | 103B | 43.50 | 29.80| 53.28 | 24.32 | 44.91 | 59.66 | 67.30 | 46.11| +| TinyLlama-1.1B-intermediate-step-240k-503b| 503B | 49.56 |31.40 |55.80 |26.54 |48.32 |56.91 |69.42 | 48.28 | +| TinyLlama-1.1B-intermediate-step-480k-1007B | 1007B | 52.54 | 33.40 | 55.96 | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 | +| TinyLlama-1.1B-intermediate-step-715k-1.5T | 1.5T | 53.68 | 35.20 | 58.33 | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 | +| TinyLlama-1.1B-intermediate-step-955k-2T | 2T | 54.63 | 33.40 | 56.83 | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 | +| TinyLlama-1.1B-intermediate-step-1195k-2.5T | 2.5T | 58.96 | 34.40 | 58.72 | 31.91 | 56.78 | 63.21 | 73.07 | 53.86| +| TinyLlama-1.1B-intermediate-step-1431k-3T | 3T | 59.20 | 36.00 | 59.12 | 30.12 | 55.25 | 57.83 | 73.29 | 52.99| \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e36863d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,4 @@ +{ + "<|im_end|>": 32000, + "<|im_start|>": 32001 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..674c30f --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 32000, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 22, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.0", + "use_cache": true, + "vocab_size": 32002 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..49b6b8e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "max_length": 2048, + "pad_token_id": 0, + "transformers_version": "4.37.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..980b2cc --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f230e4eea97731689bc2d44763701d4619d8e8ffc3985152dfa84d2206aecbf0 +size 2200136248 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..1200f33 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419c3cc1dfc2f60c0f613e4e4200e3c9953934d5323bbdd8d1fc84d3eddffe77 +size 2200178286 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..40b1c6d --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c619f49 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,60 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32001": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "trust_remote_code": false, + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}